© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48538
    Prev
    Next
    INDEX
    Explanations

    exclusive content and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ingenious
    -0.11
     endlessly
    -0.11
     independents
    -0.11
     barr
    -0.10
     neat
    -0.10
    ipel
    -0.10
    serter
    -0.10
    aines
    -0.10
    ĵĺ
    -0.10
    964
    -0.10
    POSITIVE LOGITS
     access
    0.16
     insights
    0.12
    access
    0.12
     content
    0.12
     footage
    0.11
     insight
    0.11
    /private
    0.11
     glimps
    0.10
    -access
    0.10
     acces
    0.10
    Activations Density 0.019%

    No Known Activations